© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7558
    Prev
    Next
    INDEX
    Explanations

    cost-effectiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    charg
    -0.08
    /column
    -0.07
    ÃŃas
    -0.07
    SCO
    -0.07
     Kirst
    -0.07
    pts
    -0.07
    645
    -0.07
     spoken
    -0.07
    EMENT
    -0.07
    icas
    -0.07
    POSITIVE LOGITS
    lier
    0.22
    umed
    0.22
    -effective
    0.21
    liest
    0.21
    umer
    0.20
    -effect
    0.19
    ochond
    0.18
    umes
    0.18
    ello
    0.17
    uming
    0.17
    Activations Density 0.043%

    No Known Activations